Complex backgrounds, significant target size variations, and severe sea clutter in maritime infrared imagery often result in missed or false detections. To address this challenge, an improved method based on YOLOv8n, termed maritime infrared target detection-YOLO (MITD-YOLO), is proposed to enhance target detection accuracy in maritime infrared images.

MITD-YOLO incorporates a diverse branch module (DBB) and enhanced multi-scale convolution (EMSConv) to leverage multi-scale convolutions, enabling the model to more effectively capture complex features. A triple attention mechanism is employed to facilitate spatial and channel-wise feature interaction, thereby improving key feature extraction. Additionally, the powerful-IoUv2 (PIoUv2) loss function is introduced to address the anchor box expansion problem, leading to improved detection accuracy and enhanced model robustness.

Experimental results show that the improved model significantly enhances the efficiency of maritime infrared target detection, with a 2.3% increase in precision and a 1.7% increase in recall. The model achieves an average precision of 88.9%, and 132.8 FPS, outperforming the original model.

MITD-YOLO enhances maritime infrared target detection performance and provides a more reliable target detection technology for applications such as maritime surveillance and ship navigation, contributing to the advancement of intelligent maritime systems.

In order to meet the development requirements of intelligent shipping and the domestication of meteorological navigation in China, a ship multi-objective route planning method based on the fusion of A* and non-dominated sorting genetic algorithm II (NSGA-II) is proposed that can adapt to complex and diverse long-distance navigation tasks.

By incorporating the A* algorithm into NSGA-II to guide the search direction and accelerate the convergence speed, an environmental data model and objective functions are constructed. Simulation verification is then performed using the trans-Pacific route.

The simulation results demonstrate that the proposed model and algorithm can obtain a uniformly distributed and diversified Pareto optimal route set. All routes can successfully avoid areas with severe weather conditions, and the most suitable route for the ship can be selected according to the decision-makers' needs.

In summary, the proposed method can be applied to optimize ship ocean routes under multiple constraint conditions and identify routes that meet the voyage objectives, thereby reducing operational costs, improving shipping efficiency and providing support for ship meteorological navigation and future intelligent ship navigation.